Audit: broken code
SkillDev toolsAudit dimension - find broken code by running every committed verification instrument and tabling deltas against the recorded baselines. Invoked by dr-audit-orchestrator when broken.md is missing.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Audit: broken code skill
What this skill tells your AI
The instructions your AI receives, as published by ahepi/deepreason in .claude/skills/dr-audit-broken/SKILL.md and read by ahel’s review.
Entry: LEDGER.md exists, broken.md missing. Exit: broken.md
written, LEDGER rows added, proofs in proof/.
Broken means: an instrument's output moved from
docs/AUDIT_BASELINES.md §Instruments. The instruments define
broken; this worker adds no judgment of its own (G3).
Operations
pip install -e . --break-system-packages -qandpip install pytest pytest-xdist jsonschema --break-system-packages -q. Run every command below withpython -mwhere applicable; save each full output toproof/broken-<n>.txt.python -m pytest tests/ -q -n 4— compare failures to the baseline failure list. Re-run any non-baseline failure serially (python -m pytest <nodeid> -q) before rowing it: still red → verdictbroken; green serially → verdictflaky(row it; flaky is a finding unless baseline-listed).python tools/docs_verify.py— compare failing checks to the baseline list. Non-baseline failure → verdictbroken(the check or the code it pins moved; the fix tranche decides which).python scripts/wheel_smoke.pythenpython -u scripts/wheel_operational_smoke.py— any non-zero exit → verdictbroken, target = the pin named in the output.- RETIRED (operator ruling 2026-08-22, CLAUDE.md §Build and test):
the root sweep is no longer an audit instrument. Do NOT run
tools/root_sweep.py. Writeproof/broken-sweep.txtcontaining the single lineretired 2026-08-22 — see CLAUDE.mdso the proof count stays auditable. - Write
broken.md: the table of every non-baseline delta, one row per finding, columns as the LEDGER. Matches baseline exactly → the table plus one line:all instruments at baseline, with the five proof files as the required proof of looking (G2).
GATE
Pass: every instrument ran (four live instruments + the retirement
marker file = five proof files) AND every non-baseline delta has a
LEDGER row with disposition parked.
Verdict labels: broken | flaky | baseline.
Activation plant (first run)
Edit one assert in a copy of a passing test to a false constant, run
step 2 scoped to that file, paste the red output, git checkout --
the file, paste the clean status.
Outlets
| Situation | Outlet |
|---|---|
| Any fix impulse | PARK — prompt in PARKED.md, route deepreason-orchestrator |
| Instrument itself crashes | row verdict broken, target = instrument, PARK |
| Baseline looks wrong | row it, PARK a baseline-correction prompt (PRECEDENCE 2) |
Signals
- GitHub stars
- 142
- Forks
- 14
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
dr-audit-broken- Source
- github.com/ahepi/deepreason